data-science-python-stack
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a comprehensive and opinionated list of Python libraries for data science, organized into logical tiers (Mandatory, User Choice, Optional, Transitive).\n- [SAFE]: Instructions focus on proper environment management using standard tools like pixi, uv, and conda via an external
python-env-managerskill.\n- [SAFE]: No evidence of malicious patterns such as prompt injection, data exfiltration, or obfuscation was found. External links point to official vendor documentation (probabl-ai).\n- [SAFE]: The stack relies on well-known open-source libraries (scikit-learn,pandas,pytorch, etc.) and vendor-specific tools (skore,skrub) that are consistent with the author's identity.
Audit Metadata